A locomotive vibration performance evaluation method and system based on locomotive value traceability

Abstract

The present invention relates to the field of vibration detection technology, and includes a locomotive vibration performance assessment method and system based on locomotive measurement traceability, comprising the following steps: obtaining reference light and measurement light; modulating the measurement light according to a pulse modulation signal using an acousto-optic modulator to obtain a measurement pulse light; calculating a reverse signal of the sound signal to drive a piezoelectric driver to vibrate a detection optical fiber; directing the measurement pulse light into the detection optical fiber, deriving a back-Rayleigh signal generated by the measurement pulse light in the detection optical fiber, and obtaining an anti-ambient sound back-Rayleigh signal; performing guided edge filtering on the anti-ambient sound back-Rayleigh signal to obtain a filtered back-Rayleigh signal; coupling the filtered back-Rayleigh signal with the reference light to obtain an electrical signal; converting the electrical signal into a vibration frequency signal using an IQ demodulator, evaluating the signal using an assessment model, and assessing the vehicle health status based on the vibration frequency signal. The present invention can improve the accuracy of locomotive vibration performance assessment.

Description

Technical Field

[0001] The present invention relates to the field of vibration detection technology, and in particular to a locomotive vibration performance evaluation method and system based on locomotive value traceability. Background Art

[0002] As a core tool for road transportation, locomotive operating conditions are directly related to transport efficiency and passenger safety. The vibrations generated by locomotives during operation not only affect passenger comfort but can also cause structural fatigue and premature failure. Therefore, evaluating and monitoring locomotive vibration performance is particularly important.

[0003] Traditional locomotive vibration monitoring methods typically rely on contact sensors such as accelerometers, velocimeters, and displacement meters. However, these sensors still face limitations in modern railway transportation systems, such as accuracy, range, installation, and maintenance. As time goes by, these measurements, often with significant errors, no longer meet the demand for accurate locomotive measurements. Summary of the Invention

[0004] The present invention provides a locomotive vibration performance evaluation method and system based on locomotive measurement value traceability, the main purpose of which is to improve the accuracy of locomotive vibration performance evaluation based on locomotive measurement value traceability through an anti-interference phase-sensitive optical time domain reflectometry measurement method and an artificial intelligence evaluation method.

[0005] To achieve the above-mentioned purpose, the present invention provides a locomotive vibration performance evaluation method based on locomotive value traceability, comprising:

[0006] Acquiring sound signals using sound sensors at preset key positions of the vehicle, and acquiring reference light and measurement light using laser emitters and spectrometers at the key positions of the vehicle;

[0007] Obtaining a pulse modulation signal of a preset intensity, and using a pre-built acousto-optic modulator to modulate the measuring light according to the pulse modulation signal to obtain a measuring pulse light;

[0008] Calculating the average decibel level of the sound signal within a preset time period, and determining whether the average decibel level is greater than a preset interference threshold;

[0009] When the average decibel is greater than the interference threshold, calculating a reverse signal of the sound signal, and driving a pre-built piezoelectric actuator according to the reverse signal to vibrate the pre-built detection optical fiber;

[0010] When the average decibel is less than or equal to the interference threshold, the measuring pulse light is introduced into the detection optical fiber, and a pre-built circulator is used to derive a back Rayleigh signal generated by the measuring pulse light in the detection optical fiber to obtain an anti-ambient sound back Rayleigh signal;

[0011] Performing guided edge filtering detection on the anti-ambient sound back Rayleigh signal to obtain a filtered back Rayleigh signal;

[0012] Using a pre-built coupler, coupling the filtered back Rayleigh signal and the reference light to obtain a coupled signal, and using a pre-built balanced detector to convert the coupled signal into an electrical signal;

[0013] Using a pre-built IQ demodulator, the electrical signal is demodulated according to a preset local reference signal to obtain an I-path signal and a Q-path signal, and using a pre-built host computer, the vibration frequency signal at the key position of the vehicle is calculated based on the I-path signal and the Q-path signal;

[0014] The pre-trained vehicle condition assessment model is used to perform correlation identification on the vibration frequency signals at each key position of the vehicle based on the fault vibration characteristics to obtain the vehicle health status.

[0015] Optionally, the laser emitter is an infrared laser emitter with a wavelength greater than 1 mm, and the splitting ratio between the reference light and the measurement light of the spectrometer is 1:9.

[0016] Optionally, the using a pre-built acousto-optic modulator to modulate the measurement light according to the pulse modulation signal to obtain the measurement pulse light includes:

[0017] Performing radio frequency amplification on the pulse modulation signal to obtain a high-energy modulation signal, wherein the pulse width of the pulse modulation signal is 100 ns;

[0018] using a piezoelectric transducer in a pre-built acousto-optic modulator to convert the high-energy modulated signal into ultrasonic waves;

[0019] Using the ultrasonic wave to change the refractive index of the medium in the acousto-optic modulator, and modulating the measuring light into a primary measuring pulse light according to the medium after the refractive index change;

[0020] The primary measuring pulse light is configured with a preset frequency shift of 200 MHz to obtain a measuring pulse light.

[0021] Optionally, calculating a reverse signal of the sound signal and driving a piezoelectric driver according to the reverse signal to vibrate a pre-constructed detection optical fiber includes:

[0022] amplifying and filtering the sound signal to obtain a noise reduction signal, and digitizing the noise reduction signal to obtain a digital signal;

[0023] Performing a spectrum characteristic analysis on the digital signal using Fourier transform to obtain a main frequency of the signal, and performing an inverse operation on the main frequency of the signal to obtain a main frequency offset;

[0024] A pre-built detection fiber is vibrated according to the offset primary frequency using a pre-built piezoelectric actuator.

[0025] Optionally, performing guided edge filtering detection on the anti-ambient sound back Rayleigh signal to obtain a filtered back Rayleigh signal includes:

[0026] Constructing a two-dimensional space-time matrix based on the length of the detection optical fiber and a preset time signal, wherein each row in the two-dimensional space-time matrix represents the amplitude of the anti-ambient sound back-Rayleigh signal generated by the measurement pulse light, and each column represents the signal intensity at the same optical fiber position at different times;

[0027] The space-time two-dimensional matrix is ​​configured as a two-dimensional function, and the two-dimensional function is expressed as:

[0028] ;

[0029] Where, Indicates Centered window, Represents the two-dimensional space matrix of space-time A sampling point within the range, Indicates that the two-dimensional function is The output result of the sampling point, Indicates that the anti-ambient sound back Rayleigh signal is in the The value at the sampling point, and Indicates that when the window center is at Fixed coefficient of time;

[0030] Perform gradient calculation on the two-dimensional function to obtain the gradient formula:

[0031] ;

[0032] Where, represents the gradient operator, represents the two-dimensional function, represents fixed parameters, Indicates the anti-ambient sound back Rayleigh signal;

[0033] According to the gradient formula, determining that when the anti-ambient sound back-Rayleigh signal has an edge gradient, the output result of the two-dimensional function has a similar edge gradient;

[0034] To calculate the fixed coefficient and , based on the linear representation of the two-dimensional function, construct a cost function that minimizes the difference between the output result and the anti-ambient sound back Rayleigh signal, wherein the cost function is expressed as:

[0035] ;

[0036] Where, Indicates calculation of fixed parameters The cost function of is the regularization parameter, avoiding Too big, Expressed as the two-dimensional function in The expected signal at the sampling point;

[0037] Minimize the cost function to obtain a fixed coefficient and :

[0038] ;

[0039] Where, Indicates the window The amount of data in and The anti-ambient sound back Rayleigh signal In the window The mean and variance of , Indicates expected signal In the window The mean of

[0040] According to the fixed coefficient and , calculate the two-dimensional function to obtain a smooth two-dimensional function that preserves edge information:

[0041] ;

[0042] in,

[0043] ;

[0044] Where, Display window Each within the range Fixed coefficient at sampling point The average value of Display window Each within the range Fixed coefficient at sampling point The average value of

[0045] Using a pre-built Sobel operator, a convolution operation is performed on the smooth two-dimensional function to obtain the gradient of the smooth two-dimensional function in the horizontal direction, and based on the gradient, the edge information of the anti-ambient sound back-Rayleigh signal is obtained, wherein the vertical template in the Sobel operator is expressed as:

[0046] ;

[0047] Where, Represents the 4×4 vertical template in the Sobel operator;

[0048] The length of the detection optical fiber is set to n, and the signal of the detection optical fiber is collected according to a preset distance collection standard to obtain edge information of n anti-ambient sound back-Rayleigh signals, and the edge information of the n anti-ambient sound back-Rayleigh signals is differentially calculated according to the amplitude difference method to obtain a filtered back-Rayleigh signal.

[0049] Optionally, the coupler is a 50:50 beam splitter.

[0050] Optionally, before using a pre-built IQ demodulator to demodulate the electrical signal according to a preset local reference signal, the method further includes:

[0051] amplifying the electrical signal to obtain an amplified electrical signal;

[0052] filtering the amplified electrical signal to obtain a filtered electrical signal;

[0053] The filtered electrical signal is sent to a pre-built IQ demodulator.

[0054] Optionally, the using a pre-built IQ demodulator to demodulate the electrical signal according to a preset local reference signal to obtain an I-path signal and a Q-path signal includes:

[0055] Using a local oscillator in a pre-built IQ demodulator, a local reference signal is generated, where the local reference signal has the same frequency as the electrical signal but has a different phase or amplitude;

[0056] Mixing the local reference signal and the electrical signal to obtain a mixed signal;

[0057] Calculating the difference between the in-phase component of the electrical signal and the local reference signal according to the mixed signal to obtain an I-channel signal;

[0058] The difference between the electric signal and the quadrature component of the local reference signal is calculated according to the mixed signal to obtain a Q-path signal.

[0059] Optionally, the pre-trained vehicle condition assessment model is used to perform correlation identification based on fault vibration characteristics on the vibration frequency signals at each key position of the vehicle to obtain the vehicle health status, including:

[0060] Using a pre-trained vehicle condition assessment model, a feature extraction operation is performed on the vibration frequency signal at each key position of the vehicle to obtain a feature vector;

[0061] Performing an outlier extraction operation on the feature vector to obtain an abnormal feature vector;

[0062] Using a pre-built anomaly database, clustering the anomaly feature vectors to obtain clustering scores for each anomaly type, and extracting anomaly types whose clustering scores are greater than a preset warning threshold;

[0063] The abnormal types at key positions of each vehicle are uniformly output to obtain the vehicle health status.

[0064] To achieve the above-mentioned purpose, the present invention further provides a locomotive vibration performance evaluation system based on locomotive value traceability, comprising:

[0065] a data capture module configured to acquire sound signals using sound sensors at preset key positions on the vehicle, acquire reference light and measurement light using laser emitters and spectrometers at the key positions on the vehicle, and acquire a pulse modulation signal of preset intensity, and modulate the measurement light according to the pulse modulation signal using a pre-built acousto-optic modulator to obtain measurement pulse light;

[0066] a sound vibration cancellation module, configured to calculate an average decibel of the sound signal within a preset time period, determine whether the average decibel is greater than a preset interference threshold, and when the average decibel is greater than the interference threshold, calculate a reverse signal of the sound signal, and drive a pre-constructed piezoelectric actuator according to the reverse signal to vibrate the pre-constructed detection optical fiber;

[0067] a vibration signal acquisition module, configured to, when the average decibel is less than or equal to the interference threshold, introduce the measurement pulse light into the detection optical fiber, utilize a pre-built circulator to derive the back Rayleigh signal generated by the measurement pulse light in the detection optical fiber to obtain an anti-ambient sound back Rayleigh signal, perform guided edge filtering detection on the anti-ambient sound back Rayleigh signal to obtain a filtered back Rayleigh signal, couple the filtered back Rayleigh signal and the reference light to obtain a coupled signal, convert the coupled signal into an electrical signal using a pre-built coupler and a pre-built balanced detector, and utilize a pre-built IQ demodulator to demodulate the electrical signal according to a preset local reference signal to obtain an I-path signal and a Q-path signal, and utilize a pre-built host computer to calculate the vibration frequency signal at the key position of the vehicle according to the I-path signal and the Q-path signal;

[0068] The vehicle vibration performance evaluation module is used to use a pre-trained vehicle condition evaluation model to perform correlation identification on the vibration frequency signals at each key position of the vehicle based on the fault vibration characteristics to obtain the vehicle health status.

[0069] In order to solve the above problem, the present invention further provides an electronic device, comprising:

[0070] a memory storing at least one instruction; and

[0071] The processor executes the instructions stored in the memory to implement the locomotive vibration performance evaluation method based on locomotive value tracing.

[0072] In order to solve the above problems, the present invention also provides a computer-readable storage medium, which stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned locomotive vibration performance evaluation method based on locomotive value traceability.

[0073] The present invention addresses the problems described in the background art. First, a sound sensor and a laser detector are installed at key locations on the vehicle. The laser detector includes a laser emitter and a spectrometer. The spectrometer separates the laser light into a measurement light for measuring vehicle vibration and a reference light for comparison. The present invention employs phase-sensitive optical time-domain reflectometry to measure vibration. Considering that vehicles are noisy and the measuring tool is a relatively thin optical fiber, the present invention first uses a reverse signal to offset sound interference through a piezoelectric driver to improve vibration detection accuracy. Furthermore, before identifying the vehicle vibration signal based on the back-directed Rayleigh signal, the present invention further reduces the signal-to-noise ratio in the back-directed Rayleigh signal through guided filtering, edge computing, and amplitude differentiation, thereby further improving the accuracy of vehicle vibration signal acquisition. Finally, the present invention evaluates vehicle vibration performance through the accuracy and timeliness of AI calculations by training an artificial intelligence model, obtaining a final vehicle health status. Therefore, the method and system proposed by the present invention can improve the accuracy of locomotive vibration performance assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 A schematic flow chart of a locomotive vibration performance evaluation method based on locomotive value traceability provided by one embodiment of the present invention;

[0075] Figure 2 This is a functional module diagram of a locomotive vibration performance evaluation system based on locomotive value traceability provided by one embodiment of the present invention;

[0076] Figure 3 A schematic structural diagram of an electronic device for implementing the locomotive vibration performance evaluation method based on locomotive value traceability provided by one embodiment of the present invention.

[0077] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0078] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0079] The embodiment of the present application provides a locomotive vibration performance evaluation method based on locomotive measurement value traceability. The execution subject of the locomotive vibration performance evaluation method based on locomotive measurement value traceability includes but is not limited to at least one of the electronic devices such as the server and the terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the locomotive vibration performance evaluation method based on locomotive measurement value traceability can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0080] Reference Figure 1 FIG. 1 is a flow chart of a locomotive vibration performance evaluation method based on locomotive measurement value traceability according to an embodiment of the present invention. In this embodiment, the locomotive vibration performance evaluation method based on locomotive measurement value traceability includes:

[0081] S1. Acquire sound signals using sound sensors at preset key positions of the vehicle, and acquire reference light and measurement light using laser emitters and spectrometers at the key positions of the vehicle.

[0082] In the embodiment of the present invention, the φ-OTDR technology is mainly used to measure the vibration signal data of the locomotive, and some anti-interference algorithms are added to the φ-OTDR technology to improve the accuracy of vibration signal extraction.

[0083] It should be noted that the φ-OTDR technology includes a laser generator, a beam splitter, an acousto-optic modulator, a circulator, an optical fiber, a coupler, a balanced detector, an amplifier, a filter, an IQ demodulator, and a host computer. The traditional approach primarily involves using a beam splitter to separate the laser light into measurement light and reference light. The measurement light is affected by factors such as fiber medium inhomogeneities in the optical fiber, causing it to undergo reverse Rayleigh scattering, resulting in a backscattered Rayleigh signal. When the locomotive vibrates, the optical fiber vibrates, causing the laser light to change within the fiber, and consequently, the backscattered Rayleigh signal. The reference light is used to monitor the degree of change in the backscattered Rayleigh signal, ultimately allowing the host computer to infer the locomotive's vibration signature.

[0084] However, in the case of locomotive vibration, there is high noise, and the detection device is a relatively small optical fiber, which is easily disturbed by the sound and generates vibration, resulting in inaccurate detection results. Therefore, the present invention is equipped with sound sensors at key positions on the vehicle.

[0085] Specifically, in an embodiment of the present invention, the laser emitter is an infrared laser emitter, such as a laser emitter with a central wavelength of 1550 nm and a line width of 3 kHz, wherein the infrared wavelength refers to a wave between 700 nm and 1 mm. The infrared laser used in the present invention has the advantages of low energy, little harm to humans, and high penetration.

[0086] Furthermore, in the embodiment of the present invention, a spectrometer with a splitting ratio of 1:9 between the reference light and the measurement light is used to ensure that the reference light and the subsequently extracted back Rayleigh signal are on the same order of magnitude, thereby improving detection accuracy.

[0087] S2. Obtain a pulse modulation signal of a preset intensity, and use a pre-built acousto-optic modulator to modulate the measurement light according to the pulse modulation signal to obtain a measurement pulse light.

[0088] In the embodiment of the present invention, experimental data show that it is more appropriate for the pulse modulation signal to use a pulse signal with a preset pulse width of 100ns, and its specific value can be adjusted according to the type of vehicle and the environment.

[0089] The pulse modulation signal is a synchronization pulse for the subsequent measurement pulse light.

[0090] In detail, in an embodiment of the present invention, the method of using a pre-built acousto-optic modulator to modulate the measurement light according to the pulse modulation signal to obtain the measurement pulse light includes:

[0091] Performing radio frequency amplification on the pulse modulation signal to obtain a high-energy modulation signal, wherein the pulse width of the pulse modulation signal is 100 ns;

[0092] using a piezoelectric transducer in a pre-built acousto-optic modulator to convert the high-energy modulated signal into ultrasonic waves;

[0093] Using the ultrasonic wave to change the refractive index of the medium in the acousto-optic modulator, and modulating the measuring light into a primary measuring pulse light according to the medium after the refractive index change;

[0094] The primary measuring pulse light is configured with a preset frequency shift of 200 MHz to obtain a measuring pulse light.

[0095] Specifically, in this embodiment of the present invention, an acousto-optic modulator converts a pulse modulation signal into ultrasonic waves. These ultrasonic waves alter the refractive index of the medium (crystal or glass), preventing the refracted primary measurement pulse from entering the subsequent optical fiber. Once the pulse stops, the medium returns to normal, allowing the primary measurement pulse to enter the optical fiber again, thereby utilizing the pulse modulation signal to control the optical fiber's operating frequency. Furthermore, to achieve better detection results, the present invention incorporates a 200 MHz frequency shift on top of the primary measurement pulse.

[0096] S3. Calculate the average decibel of the sound signal within a preset time period, and determine whether the average decibel is greater than a preset interference threshold.

[0097] In this embodiment of the present invention, the degree of sound collection varies depending on the vehicle's operating horsepower, driving location (private courtyard, public intersection, etc.), and the location of key vehicle locations (inside the cab, outside the cab). If the sound level is low, for example, less than 30 decibels, it may not significantly affect subsequent light measurement fluctuations, and vibration cancellation is not required. Otherwise, vibration cancellation is required.

[0098] When the average decibel is greater than the interference threshold, S4, calculating a reverse signal of the sound signal, and driving a pre-built piezoelectric driver according to the reverse signal to vibrate the pre-built detection optical fiber.

[0099] The reverse signal refers to the positive and negative reversal of the sound signal, which is similar to the active noise reduction principle of headphones.

[0100] In detail, in an embodiment of the present invention, the step of calculating the reverse signal of the sound signal and driving a pre-built piezoelectric driver according to the reverse signal to vibrate the pre-built detection optical fiber includes:

[0101] amplifying and filtering the sound signal to obtain a noise reduction signal, and digitizing the noise reduction signal to obtain a digital signal;

[0102] Performing a spectrum characteristic analysis on the digital signal using Fourier transform to obtain a main frequency of the signal, and performing an inverse operation on the main frequency of the signal to obtain a main frequency offset;

[0103] A pre-built detection fiber is vibrated according to the offset primary frequency using a pre-built piezoelectric actuator.

[0104] In this embodiment of the present invention, acoustic wave cancellation is achieved by generating a reverse signal. This cancellation process uses a reverse digital signal to identify the dominant frequency of the ambient sound. This frequency is then converted into vibrations using a PZT (Lead Zirconate Titanate) ceramic, thereby canceling the vibrations caused by the sound on the detection optical fiber. PZT is a piezoelectric material with a significant piezoelectric effect, converting the reverse signal into vibration-cancelling power.

[0105] When the average decibel is less than or equal to the interference threshold, S5, the measurement pulse light is introduced into the detection optical fiber, and the back-Rayleigh signal generated by the measurement pulse light in the detection optical fiber is derived using a pre-built circulator to obtain an anti-ambient sound back-Rayleigh signal.

[0106] In an embodiment of the present invention, the circulator is an optical isolator that allows light to be transmitted in one direction while preventing reverse transmission. The present invention can introduce the measuring pulse light into the optical fiber through the circulator, and can also extract the back-direction Rayleigh signal generated in the optical fiber in the opposite direction to the measuring pulse light from the optical fiber and send it to the coupler.

[0107] Since the detection optical fiber has undergone noise vibration cancellation by the PZT, the extracted back Rayleigh signal can be referred to as an anti-ambient sound back Rayleigh signal.

[0108] S6. Perform guided edge filtering detection on the anti-ambient sound back Rayleigh signal to obtain a filtered back Rayleigh signal.

[0109] In detail, in an embodiment of the present invention, performing guided edge filtering detection on the anti-ambient sound back Rayleigh signal to obtain a filtered back Rayleigh signal includes:

[0110] Constructing a two-dimensional space-time matrix based on the length of the detection optical fiber and a preset time signal, wherein each row in the two-dimensional space-time matrix represents the amplitude of the anti-ambient sound back-Rayleigh signal generated by the measurement pulse light, and each column represents the signal intensity at the same optical fiber position at different times;

[0111] The space-time two-dimensional matrix is ​​configured as a two-dimensional function, and the two-dimensional function is expressed as:

[0112] ;

[0113] Where, Indicates Centered window, Represents the two-dimensional space matrix of space-time A sampling point within the range, Indicates that the two-dimensional function is The output result of the sampling point, Indicates that the anti-ambient sound back Rayleigh signal is in the The value at the sampling point, and Indicates that when the window center is at Fixed coefficient of time;

[0114] Perform gradient calculation on the two-dimensional function to obtain the gradient formula:

[0115] ;

[0116] Where, represents the gradient operator, represents the two-dimensional function, represents fixed parameters, Indicates the anti-ambient sound back Rayleigh signal;

[0117] According to the gradient formula, determining that when the anti-ambient sound back-Rayleigh signal has an edge gradient, the output result of the two-dimensional function has a similar edge gradient;

[0118] To calculate the fixed coefficient and , based on the linear representation of the two-dimensional function, construct a cost function that minimizes the difference between the output result and the anti-ambient sound back Rayleigh signal, wherein the cost function is expressed as:

[0119] ;

[0120] Where, Indicates calculation of fixed parameters The cost function of is the regularization parameter, avoiding Too big, Expressed as the two-dimensional function in The expected signal at the sampling point;

[0121] Minimize the cost function to obtain a fixed coefficient and :

[0122] ;

[0123] Where, Indicates the window The amount of data in and The anti-ambient sound back Rayleigh signal In the window The mean and variance of , Indicates expected signal In the window The mean of

[0124] According to the fixed coefficient and , calculate the two-dimensional function to obtain a smooth two-dimensional function that preserves edge information:

[0125] ;

[0126] in,

[0127] ;

[0128] Where, Display window Each within the range Fixed coefficient at sampling point The average value of Display window Each within the range Fixed coefficient at sampling point The average value of

[0129] Using a pre-built Sobel operator, a convolution operation is performed on the smooth two-dimensional function to obtain the gradient of the smooth two-dimensional function in the horizontal direction, and based on the gradient, the edge information of the anti-ambient sound back-Rayleigh signal is obtained, wherein the vertical template in the Sobel operator is expressed as:

[0130] ;

[0131] Where, Represents the 4×4 vertical template in the Sobel operator;

[0132] The length of the detection optical fiber is set to n, and the signal of the detection optical fiber is collected according to a preset distance collection standard to obtain edge information of n anti-ambient sound back-Rayleigh signals, and the edge information of the n anti-ambient sound back-Rayleigh signals is differentially calculated according to the amplitude difference method to obtain a filtered back-Rayleigh signal.

[0133] According to the above steps, the present invention first constructs a two-dimensional space-time matrix of the anti-ambient sound back-Rayleigh signal collected by the φ-OTDR system according to a specified fiber length. Next, the two-dimensional space-time matrix is ​​subjected to edge-preserving guided filtering to enhance the visibility of external vibration information. Edge detection is then performed on the two-dimensional matrix after guided filtering to extract distinct edge features. Finally, amplitude differentiation processing and normalization are performed to obtain the final result.

[0134] Specifically, during the two-dimensional space construction process, the total length of the detection fiber is n. Since a signal is collected every 1 / n of the length, the total number of collection points is n. The size of n determines the two-dimensional space-time matrix. In the two-dimensional matrix, each row represents the amplitude of the anti-ambient sound backscattered Rayleigh signal generated by the detection pulse light, and each column represents the signal strength at the same fiber position at different times.

[0135] In the guided filtering process, the time-space two-dimensional space matrix is ​​first guided filtered in order to smooth a portion of the noise while retaining the edges with valid information. Then, the time-space two-dimensional space matrix is ​​regarded as the two-dimensional function described in the above steps using a local linear model. The present invention takes the gradient of the two-dimensional function. It can be seen that when the guided object (anti-ambient sound back-to-Rayleigh signal) has an edge gradient, the output result of the two-dimensional function will also have a corresponding gradient. Therefore, after guided filtering, the edges of valid information can be retained. In order to further determine the fixed coefficient and , then it is necessary to consider the expected signal (real signal) of the two-dimensional function. In order to retain the effective vibration information and minimize the difference between the output result and the expected signal, the cost function in the above steps is constructed and solved to obtain the optimal fixed coefficient and Finally, by importing these two fixed coefficients into the original two-dimensional function, we can obtain a two-dimensional function that only smooths the middle of the two-dimensional function but not the edges.

[0136] Then, the present invention obtains a filtered backward Rayleigh signal with a low signal-to-noise ratio through the above-mentioned edge detection and amplitude difference operations. The edge detection and amplitude difference operations are relatively simple, and their specific operation steps are not repeated here.

[0137] S7. Use a pre-built coupler to couple the filtered back Rayleigh signal and the reference light to obtain a coupled signal, and use a pre-built balanced detector to convert the coupled signal into an electrical signal.

[0138] The 50:50 beam splitter used in the embodiment of the present invention is used as a coupler to couple the filtered back Rayleigh signal and the reference light in equal proportions.

[0139] S8. Using a pre-built IQ demodulator, demodulate the electrical signal according to a preset local reference signal to obtain an I-path signal and a Q-path signal, and using a pre-built host computer, calculate the vibration frequency signal at the key position of the vehicle based on the I-path signal and the Q-path signal.

[0140] In an embodiment of the present invention, before using a pre-built IQ demodulator to demodulate the electrical signal according to a preset local reference signal, the method further includes:

[0141] amplifying the electrical signal to obtain an amplified electrical signal;

[0142] filtering the amplified electrical signal to obtain a filtered electrical signal;

[0143] The filtered electrical signal is sent to a pre-built IQ demodulator.

[0144] Among them, gain is performed through an amplifier to increase the strength of the signal; unnecessary frequency components in the signal, such as noise or frequencies unrelated to the target signal, can be removed through a bandpass filter, a low-pass filter, or a high-pass filter; the above process is a preprocessing process before the IQ demodulator processes the signal, which can effectively improve processing accuracy.

[0145] Furthermore, in an embodiment of the present invention, the method of using a pre-built IQ demodulator to demodulate the electrical signal according to a preset local reference signal to obtain an I-path signal and a Q-path signal includes:

[0146] Using a local oscillator in a pre-built IQ demodulator, a local reference signal is generated, where the local reference signal has the same frequency as the electrical signal but has a different phase or amplitude;

[0147] Mixing the local reference signal and the electrical signal to obtain a mixed signal;

[0148] Calculating the difference between the in-phase component of the electrical signal and the local reference signal according to the mixed signal to obtain an I-channel signal;

[0149] The difference between the electric signal and the quadrature component of the local reference signal is calculated according to the mixed signal to obtain a Q-path signal.

[0150] In this embodiment of the present invention, demodulation techniques are used to mix the amplified and filtered signal with a reference signal (local reference signal) generated by a local oscillator (LO). The reference signal (local reference signal) typically has the same frequency as the carrier signal (electrical signal), but with a different phase or amplitude to match the I and Q components of the received signal.

[0151] In a φ-OTDR system, IQ demodulation is used to extract vibration and strain information from the reflected, filtered, backscattered Rayleigh signal. By analyzing changes in the I and Q signals, small disturbances along the fiber can be detected, enabling high-precision distributed sensing.

[0152] S9. Using a pre-trained vehicle condition assessment model, perform correlation identification based on fault vibration characteristics on the vibration frequency signals at each key position of the vehicle to obtain the vehicle health status.

[0153] The vehicle condition assessment model described in the embodiment of the present invention is a Transformer-based neural network model, which can perform one-time feature extraction on the vibration signal frequencies of multiple sources and perform anomaly detection and correlation detection on the extracted features.

[0154] In the embodiment of the present invention, the model can be trained by using pre-constructed training samples, a gradient descent method, and a cross-entropy loss algorithm, and the model training progress can be controlled by testing the accuracy of the model.

[0155] In detail, in an embodiment of the present invention, the pre-trained vehicle condition assessment model is used to perform correlation identification based on fault vibration characteristics on the vibration frequency signals at each key position of the vehicle to obtain the vehicle health status, including:

[0156] Using a pre-trained vehicle condition assessment model, a feature extraction operation is performed on the vibration frequency signal at each key position of the vehicle to obtain a feature vector;

[0157] Performing an outlier extraction operation on the feature vector to obtain an abnormal feature vector;

[0158] Using a pre-built anomaly database, clustering the anomaly feature vectors to obtain clustering scores for each anomaly type, and extracting anomaly types whose clustering scores are greater than a preset warning threshold;

[0159] The abnormal types at key positions of each vehicle are uniformly output to obtain the vehicle health status.

[0160] The abnormality database refers to a set of recorded data obtained by damaging different areas of a locomotive or installing and using parts that are about to be scrapped to perform vibration detection during an experimental process.

[0161] Furthermore, in the embodiment of the present invention, the warning threshold is configured to be 90%.

[0162] In the embodiment of the present invention, various fault types at key locations of each vehicle can be accurately identified based on artificial intelligence, and uniformly visualized to obtain the vehicle health status.

[0163] The present invention addresses the problems described in the background art. First, a sound sensor and a laser detector are installed at key locations on the vehicle. The laser detector includes a laser emitter and a spectrometer. The spectrometer separates the laser light into a measurement light for measuring vehicle vibration and a reference light for comparison. The present invention employs phase-sensitive optical time-domain reflectometry to measure vibration. Considering that vehicles are noisy and the measuring tool is a relatively thin optical fiber, the present invention first uses a reverse signal to offset acoustic interference through a piezoelectric driver to improve vibration detection accuracy. Furthermore, before identifying the vehicle vibration signal based on the back-directed Rayleigh signal, the present invention further reduces the signal-to-noise ratio in the back-directed Rayleigh signal through guided filtering, edge computing, and amplitude differentiation, thereby further improving the accuracy of vehicle vibration signal acquisition. Finally, the present invention evaluates vehicle vibration performance through the accuracy and timeliness of AI calculations by training an artificial intelligence model, obtaining a final vehicle health status. Therefore, the method proposed in the present invention can improve the accuracy of locomotive vibration performance assessment.

[0164] like Figure 2 , which is a functional module diagram of a locomotive vibration performance evaluation system based on locomotive value traceability provided by an embodiment of the present invention.

[0165] The locomotive vibration performance assessment system 100 based on locomotive measurement traceability described in the present invention can be installed in an electronic device. Depending on the functionality implemented, the locomotive vibration performance assessment system 100 based on locomotive measurement traceability can include a data capture module 101, an acoustic vibration cancellation module 102, a vibration signal acquisition module 103, and a vehicle vibration performance assessment module 104. A module, also referred to as a unit, is a series of computer program segments that can be executed by an electronic device processor and perform a fixed function. These are stored in the electronic device's memory.

[0166] The data capture module 101 is configured to acquire sound signals using sound sensors at preset key positions of the vehicle, acquire reference light and measurement light using laser emitters and spectrometers at the key positions of the vehicle, and acquire a pulse modulation signal of a preset intensity, and modulate the measurement light according to the pulse modulation signal using a pre-built acousto-optic modulator to obtain a measurement pulse light;

[0167] The sound vibration cancellation module 102 is configured to calculate an average decibel of the sound signal within a preset time period, determine whether the average decibel is greater than a preset interference threshold, and when the average decibel is greater than the interference threshold, calculate a reverse signal of the sound signal, and drive a pre-built piezoelectric actuator according to the reverse signal to vibrate the pre-built detection optical fiber;

[0168] The vibration signal acquisition module 103 is used to, when the average decibel is less than or equal to the interference threshold, introduce the measurement pulse light into the detection optical fiber, use a pre-built circulator to derive the back Rayleigh signal generated by the measurement pulse light in the detection optical fiber to obtain an anti-ambient sound back Rayleigh signal, use a pre-built coupler to perform guided edge filtering detection on the anti-ambient sound back Rayleigh signal to obtain a filtered back Rayleigh signal, couple the filtered back Rayleigh signal and the reference light to obtain a coupled signal, convert the coupled signal into an electrical signal using a pre-built balanced detector, and use a pre-built IQ demodulator to demodulate the electrical signal according to a preset local reference signal to obtain an I-path signal and a Q-path signal, and use a pre-built host computer to calculate the vibration frequency signal at the key position of the vehicle according to the I-path signal and the Q-path signal;

[0169] The vehicle vibration performance evaluation module 104 is configured to utilize a pre-trained vehicle condition evaluation model to perform correlation identification based on fault vibration characteristics on vibration frequency signals at various key locations of the vehicle to obtain a vehicle health status.

[0170] In detail, the modules in the locomotive vibration performance evaluation system 100 based on locomotive value traceability in the embodiment of the present invention are used in the same manner as above. Figure 1 The locomotive vibration performance evaluation method based on locomotive value traceability is the same technical means as described in , and can produce the same technical effects, so it will not be repeated here.

[0171] like Figure 3 , which is a structural diagram of an electronic device for implementing a locomotive vibration performance evaluation method based on locomotive value traceability provided by an embodiment of the present invention.

[0172] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a locomotive vibration performance evaluation method program based on locomotive value traceability.

[0173] The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 1. Furthermore, the memory 11 includes both the internal storage unit of the electronic device 1 and an external storage device. The memory 11 can be used not only to store application software installed in the electronic device 1 and various types of data, such as the code of the locomotive vibration performance evaluation method program based on locomotive measurement traceability, but can also be used to temporarily store data that has been output or is about to be output.

[0174] In some embodiments, the processor 10 may be composed of an integrated circuit, such as a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips. The processor 10 is the control core (Control Unit) of the electronic device, connecting the various components of the entire electronic device using various interfaces and circuits. It executes or runs programs or modules stored in the memory 11 (such as a locomotive vibration performance assessment method program based on locomotive measurement traceability) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0175] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0176] Figure 3 Only the electronic device with components is shown, and it can be understood by those skilled in the art that Figure 3 The structure shown does not constitute a limitation on the electronic device 1 , and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0177] For example, although not shown, the electronic device 1 may further include a power supply (e.g., a battery) to power various components. Preferably, the power supply may be logically connected to the at least one processor 10 via a power management device, thereby enabling functions such as charge management, discharge management, and power consumption management via the power management device. The power supply may further include any components such as one or more DC or AC power supplies, a recharging device, a power failure detection circuit, a power converter or inverter, and a power status indicator. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which are not further described here.

[0178] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0179] Optionally, the electronic device 1 may further include a user interface, which may be a display or an input unit (such as a keyboard). Optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display may also be appropriately referred to as a display screen or a display unit, and is used to display information processed by the electronic device 1 and to display a visual user interface.

[0180] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0181] The locomotive vibration performance evaluation method program based on locomotive value traceability stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve the following:

[0182] Acquiring sound signals using sound sensors at preset key positions of the vehicle, and acquiring reference light and measurement light using laser emitters and spectrometers at the key positions of the vehicle;

[0183] Obtaining a pulse modulation signal of a preset intensity, and using a pre-built acousto-optic modulator to modulate the measuring light according to the pulse modulation signal to obtain a measuring pulse light;

[0184] Calculating the average decibel level of the sound signal within a preset time period, and determining whether the average decibel level is greater than a preset interference threshold;

[0185] When the average decibel is greater than the interference threshold, calculating a reverse signal of the sound signal, and driving a pre-built piezoelectric actuator according to the reverse signal to vibrate the pre-built detection optical fiber;

[0186] When the average decibel is less than or equal to the interference threshold, the measuring pulse light is introduced into the detection optical fiber, and a pre-built circulator is used to derive a back Rayleigh signal generated by the measuring pulse light in the detection optical fiber to obtain an anti-ambient sound back Rayleigh signal;

[0187] Performing guided edge filtering detection on the anti-ambient sound back Rayleigh signal to obtain a filtered back Rayleigh signal;

[0188] Using a pre-built coupler, coupling the filtered back Rayleigh signal and the reference light to obtain a coupled signal, and using a pre-built balanced detector to convert the coupled signal into an electrical signal;

[0189] Using a pre-built IQ demodulator, the electrical signal is demodulated according to a preset local reference signal to obtain an I-path signal and a Q-path signal, and using a pre-built host computer, the vibration frequency signal at the key position of the vehicle is calculated based on the I-path signal and the Q-path signal;

[0190] The pre-trained vehicle condition assessment model is used to perform correlation identification on the vibration frequency signals at each key position of the vehicle based on the fault vibration characteristics to obtain the vehicle health status.

[0191] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0192] Furthermore, if the modules / units integrated into the electronic device 1 are implemented as software functional units and sold or used as independent products, they may be stored in a computer-readable storage medium. The computer-readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0193] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program. When the computer program is executed by a processor of an electronic device, the computer program can implement:

[0194] Acquiring sound signals using sound sensors at preset key positions of the vehicle, and acquiring reference light and measurement light using laser emitters and spectrometers at the key positions of the vehicle;

[0195] Obtaining a pulse modulation signal of a preset intensity, and using a pre-built acousto-optic modulator to modulate the measuring light according to the pulse modulation signal to obtain a measuring pulse light;

[0196] Calculating the average decibel level of the sound signal within a preset time period, and determining whether the average decibel level is greater than a preset interference threshold;

[0197] When the average decibel is greater than the interference threshold, calculating a reverse signal of the sound signal, and driving a pre-built piezoelectric actuator according to the reverse signal to vibrate the pre-built detection optical fiber;

[0198] When the average decibel is less than or equal to the interference threshold, the measuring pulse light is introduced into the detection optical fiber, and a pre-built circulator is used to derive a back Rayleigh signal generated by the measuring pulse light in the detection optical fiber to obtain an anti-ambient sound back Rayleigh signal;

[0199] Performing guided edge filtering detection on the anti-ambient sound back Rayleigh signal to obtain a filtered back Rayleigh signal;

[0200] Using a pre-built coupler, coupling the filtered back Rayleigh signal and the reference light to obtain a coupled signal, and using a pre-built balanced detector to convert the coupled signal into an electrical signal;

[0201] Using a pre-built IQ demodulator, the electrical signal is demodulated according to a preset local reference signal to obtain an I-path signal and a Q-path signal, and using a pre-built host computer, the vibration frequency signal at the key position of the vehicle is calculated based on the I-path signal and the Q-path signal;

[0202] The pre-trained vehicle condition assessment model is used to perform correlation identification on the vibration frequency signals at each key position of the vehicle based on the fault vibration characteristics to obtain the vehicle health status.

[0203] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only exemplary, and actual implementations may have other division methods.

[0204] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0205] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0206] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0207] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. Second-order terms are used to indicate names and do not imply any particular order.

[0208] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A locomotive vibration performance evaluation method based on locomotive value traceability, characterized in that: The method comprises: Acquiring sound signals using sound sensors at preset key positions of the vehicle, and acquiring reference light and measurement light using laser emitters and spectrometers at the key positions of the vehicle; Obtaining a pulse modulation signal of a preset intensity, and using a pre-built acousto-optic modulator to modulate the measuring light according to the pulse modulation signal to obtain a measuring pulse light; Calculating the average decibel level of the sound signal within a preset time period, and determining whether the average decibel level is greater than a preset interference threshold; When the average decibel is greater than the interference threshold, calculating a reverse signal of the sound signal, and driving a pre-built piezoelectric actuator according to the reverse signal to vibrate the pre-built detection optical fiber; When the average decibel is less than or equal to the interference threshold, the measuring pulse light is introduced into the detection optical fiber, and a pre-built circulator is used to derive a back Rayleigh signal generated by the measuring pulse light in the detection optical fiber to obtain an anti-ambient sound back Rayleigh signal; Performing guided edge filtering detection on the anti-ambient sound back Rayleigh signal to obtain a filtered back Rayleigh signal; Using a pre-built coupler, coupling the filtered back Rayleigh signal and the reference light to obtain a coupled signal, and using a pre-built balanced detector to convert the coupled signal into an electrical signal; Using a pre-built IQ demodulator, the electrical signal is demodulated according to a preset local reference signal to obtain an I-path signal and a Q-path signal, and using a pre-built host computer, the vibration frequency signal at the key position of the vehicle is calculated based on the I-path signal and the Q-path signal; The pre-trained vehicle condition assessment model is used to perform correlation identification on the vibration frequency signals at each key position of the vehicle based on the fault vibration characteristics to obtain the vehicle health status.

2. The locomotive vibration performance evaluation method based on locomotive value traceability according to claim 1, characterized in that: The laser emitter is an infrared laser emitter with a wavelength greater than 1 mm, and the splitting ratio between the reference light and the measurement light of the spectrometer is 1:

9.

3. The locomotive vibration performance evaluation method based on locomotive value traceability according to claim 2, characterized in that: The method of using a pre-built acousto-optic modulator to modulate the measurement light according to the pulse modulation signal to obtain the measurement pulse light includes: Performing radio frequency amplification on the pulse modulation signal to obtain a high-energy modulation signal, wherein the pulse width of the pulse modulation signal is 100 ns; using a piezoelectric transducer in a pre-built acousto-optic modulator to convert the high-energy modulated signal into ultrasonic waves; Using the ultrasonic wave to change the refractive index of the medium in the acousto-optic modulator, and modulating the measuring light into a primary measuring pulse light according to the medium after the refractive index change; The primary measuring pulse light is configured with a preset frequency shift of 200 MHz to obtain a measuring pulse light.

4. The locomotive vibration performance evaluation method based on locomotive value traceability according to claim 3 is characterized in that: The step of calculating a reverse signal of the sound signal and driving a pre-built piezoelectric driver according to the reverse signal to vibrate the pre-built detection optical fiber comprises: amplifying and filtering the sound signal to obtain a noise reduction signal, and digitizing the noise reduction signal to obtain a digital signal; Performing a spectrum characteristic analysis on the digital signal using Fourier transform to obtain a main frequency of the signal, and performing an inverse operation on the main frequency of the signal to obtain a main frequency offset; A pre-built detection fiber is vibrated according to the offset primary frequency using a piezoelectric actuator.

5. The locomotive vibration performance evaluation method based on locomotive value traceability according to claim 4 is characterized in that: The performing guided edge filtering detection on the anti-ambient sound back Rayleigh signal to obtain a filtered back Rayleigh signal includes: Constructing a two-dimensional space-time matrix based on the length of the detection optical fiber and a preset time signal, wherein each row in the two-dimensional space-time matrix represents the amplitude of the anti-ambient sound back-Rayleigh signal generated by the measurement pulse light, and each column represents the signal intensity at the same optical fiber position at different times; The space-time two-dimensional matrix is ​​configured as a two-dimensional function, and the two-dimensional function is expressed as: ； Where, Indicates Centered window, Represents the two-dimensional space matrix of space-time A sampling point within the range, Indicates that the two-dimensional function is The output result of the sampling point, Indicates that the anti-ambient sound back Rayleigh signal is in the The value at the sampling point, and Indicates that when the window center is at Fixed coefficient of time; Perform gradient calculation on the two-dimensional function to obtain the gradient formula: ； Where, represents the gradient operator, represents the two-dimensional function, represents fixed parameters, Indicates the anti-ambient sound back Rayleigh signal; According to the gradient formula, determining that when the anti-ambient sound back-Rayleigh signal has an edge gradient, the output result of the two-dimensional function has a similar edge gradient; To calculate the fixed coefficient and , based on the linear representation of the two-dimensional function, construct a cost function that minimizes the difference between the output result and the anti-ambient sound back Rayleigh signal, wherein the cost function is expressed as: ； Where, Indicates calculation of fixed parameters The cost function of is the regularization parameter, avoiding Too big, Expressed as the two-dimensional function in The expected signal at the sampling point; Minimize the cost function to obtain a fixed coefficient and : ； Where, Indicates the window The amount of data in and The anti-ambient sound back Rayleigh signal In the window The mean and variance of , Indicates expected signal In the window The mean of According to the fixed coefficient and , calculate the two-dimensional function to obtain a smooth two-dimensional function that preserves edge information: ； in, ； Where, Display window Each within the range Fixed coefficient at sampling point The average value of Display window Each within the range Fixed coefficient at sampling point The average value of Using a pre-built Sobel operator, a convolution operation is performed on the smooth two-dimensional function to obtain the gradient of the smooth two-dimensional function in the horizontal direction, and based on the gradient, the edge information of the anti-ambient sound back-Rayleigh signal is obtained, wherein the vertical template in the Sobel operator is expressed as: ； Where, Represents the 4×4 vertical template in the Sobel operator; The length of the detection optical fiber is set to n, and the signal of the detection optical fiber is collected according to a preset distance collection standard to obtain edge information of n anti-ambient sound back-Rayleigh signals, and the edge information of the n anti-ambient sound back-Rayleigh signals is differentially calculated according to the amplitude difference method to obtain a filtered back-Rayleigh signal.

6. The locomotive vibration performance evaluation method based on locomotive value traceability according to claim 5 is characterized in that: The coupler is a 50:50 beam splitter.

7. The locomotive vibration performance evaluation method based on locomotive value traceability according to claim 6, characterized in that: Before demodulating the electrical signal using the pre-built IQ demodulator according to a preset local reference signal, the method further includes: amplifying the electrical signal to obtain an amplified electrical signal; filtering the amplified electrical signal to obtain a filtered electrical signal; The filtered electrical signal is sent to a pre-built IQ demodulator.

8. The locomotive vibration performance evaluation method based on locomotive value traceability according to claim 7, characterized in that: The method of using a pre-built IQ demodulator to demodulate the electrical signal according to a preset local reference signal to obtain an I-path signal and a Q-path signal includes: Using a local oscillator in a pre-built IQ demodulator, a local reference signal is generated, where the local reference signal has the same frequency as the electrical signal but has a different phase or amplitude; Mixing the local reference signal and the electrical signal to obtain a mixed signal; Calculating the difference between the in-phase component of the electrical signal and the local reference signal according to the mixed signal to obtain an I-channel signal; The difference between the electric signal and the quadrature component of the local reference signal is calculated according to the mixed signal to obtain a Q-path signal.

9. The locomotive vibration performance evaluation method based on locomotive value traceability according to claim 8, characterized in that: The pre-trained vehicle condition assessment model is used to perform correlation identification based on fault vibration characteristics on the vibration frequency signals at each key position of the vehicle to obtain the vehicle health status, including: Using a pre-trained vehicle condition assessment model, a feature extraction operation is performed on the vibration frequency signal at each key position of the vehicle to obtain a feature vector; Performing an outlier extraction operation on the feature vector to obtain an abnormal feature vector; Using a pre-built anomaly database, clustering the anomaly feature vectors to obtain clustering scores for each anomaly type, and extracting anomaly types whose clustering scores are greater than a preset warning threshold; The abnormal types at key positions of each vehicle are uniformly output to obtain the vehicle health status.

10. A locomotive vibration performance evaluation system based on locomotive value traceability, characterized in that: The system comprises: a data capture module configured to acquire sound signals using sound sensors at preset key positions on the vehicle, acquire reference light and measurement light using laser emitters and spectrometers at the key positions on the vehicle, and acquire a pulse modulation signal of preset intensity, and modulate the measurement light according to the pulse modulation signal using a pre-built acousto-optic modulator to obtain measurement pulse light; a sound vibration cancellation module, configured to calculate an average decibel of the sound signal within a preset time period, determine whether the average decibel is greater than a preset interference threshold, and when the average decibel is greater than the interference threshold, calculate a reverse signal of the sound signal, and drive a pre-constructed piezoelectric actuator according to the reverse signal to vibrate the pre-constructed detection optical fiber; a vibration signal acquisition module, configured to, when the average decibel is less than or equal to the interference threshold, introduce the measurement pulse light into the detection optical fiber, utilize a pre-built circulator to derive the back Rayleigh signal generated by the measurement pulse light in the detection optical fiber to obtain an anti-ambient sound back Rayleigh signal, perform guided edge filtering detection on the anti-ambient sound back Rayleigh signal to obtain a filtered back Rayleigh signal, utilize a pre-built coupler to couple the filtered back Rayleigh signal and the reference light to obtain a coupled signal, utilize a pre-built balanced detector to convert the coupled signal into an electrical signal, utilize a pre-built IQ demodulator to demodulate the electrical signal according to a preset local reference signal to obtain an I-path signal and a Q-path signal, and utilize a pre-built host computer to calculate the vibration frequency signal at the key position of the vehicle according to the I-path signal and the Q-path signal; The vehicle vibration performance evaluation module is used to use a pre-trained vehicle condition evaluation model to perform correlation identification on the vibration frequency signals at each key position of the vehicle based on the fault vibration characteristics to obtain the vehicle health status.

Images